Air environment monitoring station equipment monitoring method and device and air environment monitoring station

Abstract

The invention relates to an air environment monitoring station equipment monitoring method and device and an air environment monitoring station, and belongs to the technical field of environment monitoring. The method comprises the steps of obtaining operation state data of air environment monitoring equipment; if it is judged that the air environment monitoring equipment is in the abnormal condition, real-time image data collected by image collection equipment is called; detecting whether a person exists in the surrounding area of the air environment monitoring equipment or not, and identifying the real-time action posture of the person by detecting the position of a key joint point of the person under the condition that the person exists; matching the real-time action posture with a pre-established equipment operation behavior library, and generating a matching result whether the real-time action posture conforms to the characteristics of operating the air environment monitoring equipment or not; and generating a diagnosis result. According to the method, matching analysis of personnel action recognition and equipment operation standards is combined, data processing and an intelligent algorithm are adopted to automatically process and analyze equipment fault problems, the problems can be quickly and accurately diagnosed and positioned, and the operation efficiency and reliability of equipment are remarkably improved.

Description

Technical Field

[0001] The present application belongs to the technical field of environmental monitoring, and specifically relates to an air environment monitoring station equipment monitoring method, device and air environment monitoring station. Background Art

[0002] Air pollution is a global public health issue. Pollutants such as particulate matter (PM2.5 and PM10), sulfur dioxide, and carbon monoxide have extremely serious impacts on human health. Air monitoring stations can provide key data, providing real-time data for urban planners and managers to help assess air quality and make scientific decisions.

[0003] At present, it is difficult to find problems in air environment monitoring stations at the first time. In terms of problem diagnosis, it usually relies on manual analysis of monitoring data, which is time-consuming and labor-intensive, and cannot detect and solve problems in a timely manner. The lack of intelligent diagnosis and analysis makes it impossible to accurately diagnose environmental problems, which is prone to misjudgment.

[0004] Therefore, how to overcome the defects of the existing air environment monitoring stations, such as difficult diagnosis, low efficiency and low accuracy, is a topic worthy of study for those skilled in the art. Summary of the invention

[0005] In view of the above analysis, the embodiments of the present invention aim to provide an air environment monitoring station equipment monitoring method, device and air environment monitoring station to solve the problems of difficult diagnosis, low efficiency and low accuracy of existing air environment monitoring stations.

[0006] In a first aspect of the present application, a method for monitoring equipment in an air environment monitoring station is provided, the method comprising: Obtain operating status data of air environment monitoring equipment; Determine whether the air environment monitoring device is in an abnormal state based on the operating status data, and if it is determined that the air environment monitoring device is in an abnormal state, call the real-time image data collected by the image acquisition device; Perform image recognition on the real-time image data to detect whether there are people in the surrounding area of ​​the air environment monitoring equipment, and if there are people, identify the real-time movement posture of the people by detecting the positions of the key joints of the people; Matching the real-time motion posture of the identified personnel with a pre-established equipment operation behavior library to generate a matching result of whether the real-time motion posture of the personnel meets the characteristics of operating the air environment monitoring equipment; wherein each standard posture model in the equipment operation behavior library is constructed based on the observation and data collection of the personnel's motion during the normal operation of the air environment monitoring equipment; When the matching result is that the person's real-time motion posture does not conform to the characteristics of operating the air environment monitoring device, the historical operation and maintenance data and air monitoring data of the air environment monitoring device are called, and a diagnosis result is generated based on the correlation between the historical operation and maintenance data, the air monitoring data and the matching result.

[0007] Optionally, performing image recognition on the real-time image data to detect whether there are people in the surrounding area of ​​the air environment monitoring device includes: Collecting large-scale images of scenes including people and equipment, including different lighting conditions, different background environments, and various gestures of people; Annotate the collected images, including whether there are people and their locations; The labeled images and labeled data are used as training sets to train the model using convolutional neural network to obtain a person recognition model; The real-time image data is input into the personnel recognition model, and the position and confidence score of the personnel are output; when the confidence score is greater than a preset threshold, the recognition result that there is a person in the surrounding area of ​​the device is output.

[0008] Optionally, matching the identified real-time motion gesture of the person with a pre-established device operation behavior library to generate a matching result of whether the real-time motion gesture of the person meets the characteristics of operating the air environment monitoring device includes: Get the real-time action posture feature vector of the person ; The real-time motion posture of the personnel includes the relative position and angle of key joints and their changes over time; The recognized real-time personnel posture feature vector Standard operation posture feature vectors with device operation behavior library Compare and calculate the similarity between the two ; When the similarity between the two is greater than the similarity threshold, it is determined that the real-time action posture of the person matches the standard posture, and a matching result is generated that the real-time action posture of the person meets the characteristics of operating the air environment monitoring device; otherwise, a matching result is generated that the real-time action posture of the person does not meet the characteristics of operating the air environment monitoring device.

[0009] Optionally, when the matching result is that the real-time motion posture of the person does not conform to the characteristics of operating the air environment monitoring device, calling the historical operation and maintenance data and air monitoring data of the air environment monitoring device, and generating a diagnosis result based on the association between the historical operation and maintenance data, the air monitoring data and the matching result includes: Integrate the operation logs, operation and maintenance records, operation records, real-time image data, and air monitoring data of air environment monitoring equipment, and align the data based on timestamps; Use an algorithm based on association rule mining to mine the association relationship between data and determine the association rules related to equipment anomalies; Based on the association rules, historical operation and maintenance data, air monitoring data and matching results are analyzed to generate diagnosis results.

[0010] Optionally, it also includes: A causal reasoning model is used to determine the causal relationship between the operation error and the equipment abnormality, and based on the inferred causal relationship, the fault cause of the equipment abnormality caused by the operation error is generated; wherein the causal reasoning model is defined based on the variables studied and the expected causal relationship in the field of air environment knowledge, and is obtained by training using data including the variables; A response suggestion is generated according to the cause of the fault, and the cause of the fault and the response suggestion are used as the diagnosis result.

[0011] Optionally, it also includes: When the matching result is that the real-time motion posture of the person does not conform to the characteristics of operating the air environment monitoring equipment, the evidence fixation event is automatically triggered: The historical operation and maintenance data and real-time image data at the time point corresponding to the posture are written into an unchangeable storage medium as evidence for data storage, and a digital signature is added to the fixed evidence and a hash value is generated.

[0012] Optionally, it also includes: An audit log for the evidence fixation event is simultaneously generated.

[0013] Optionally, judging whether the air environment monitoring device is in an abnormal state based on the operating status data includes: The operating status data of the air environment monitoring equipment is input into the fault diagnosis model, and the diagnosis result of whether the equipment is in an abnormal situation is output; the fault diagnosis model is based on big data analysis and machine learning technology, and is obtained by training large-scale training data including normal and abnormal situations.

[0014] In a second aspect of the present application, an air environment monitoring station equipment monitoring device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, an air environment monitoring station equipment monitoring method according to any one of the above-described methods is implemented.

[0015] In a third aspect of the present application, an air environment monitoring station is provided, comprising: Image acquisition devices are distributed at multiple locations of the air environment monitoring station; According to the air environment monitoring station equipment monitoring device described above; And a communication device is used to communicate with the air environment monitoring station equipment monitoring device, and output the diagnosis result when the matching result is that the real-time action posture of the person does not meet the characteristics of operating the air environment monitoring equipment.

[0016] The air environment monitoring station equipment monitoring method provided by the present application obtains the operating status data of the air environment monitoring equipment; determines whether the air environment monitoring equipment is in an abnormal state based on the operating status data, and if it is determined that the air environment monitoring equipment is in an abnormal state, calls the real-time image data collected by the image acquisition device; performs image recognition on the real-time image data to detect whether there are people in the surrounding area of ​​the air environment monitoring equipment, and identifies the real-time motion posture of the people by detecting the positions of the key joints of the people when there are people; matches the identified real-time motion posture of the people with a pre-established equipment operation behavior library, and generates a matching result of whether the real-time motion posture of the people meets the characteristics of operating the air environment monitoring equipment; when the matching result is that the real-time motion posture of the people does not meet the characteristics of operating the air environment monitoring equipment, calls the historical operation and maintenance data of the air environment monitoring equipment and the air monitoring data to generate a diagnosis result.

[0017] This application combines the matching analysis of personnel action recognition and equipment operation standards, and uses advanced data processing and artificial intelligence algorithms to automatically process and analyze equipment failure problems. It can quickly and accurately diagnose and locate problems, significantly improving the operating efficiency and reliability of the equipment. Real-time monitoring and behavior recognition improve the security of the monitoring system, ensuring the accuracy of monitoring data and the correctness of equipment operation. This application not only solves the limitations of traditional monitoring methods that cannot detect and diagnose faults in a timely manner, but also provides a comprehensive, real-time and efficient equipment management and fault diagnosis solution, significantly improving the overall operating efficiency and equipment management level of the monitoring station.

[0018] In addition, the present application also provides an air environment monitoring station equipment monitoring device and an air environment monitoring station having the above-mentioned technical effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of this specification. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0020] Figure 1A flowchart of a specific implementation method of the air environment monitoring station equipment monitoring method provided in this application; Figure 2 This is a structural block diagram of the air environment monitoring station equipment monitoring device provided in this application; Figure 3 This is a schematic diagram of the deployment of the air environment monitoring station provided for this application. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. It should be noted that, in the absence of conflict, the embodiments in the present disclosure and the features in the embodiments can be combined, separated, interchanged and / or rearranged with each other. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0022] The terms used here are for the purpose of describing specific embodiments, and are not intended to be restrictive. As used here, unless the context clearly indicates otherwise, the singular forms "one (kind, person)" and "said (the)" are also intended to include plural forms. In addition, when the terms "comprise" and / or "include" and their variations are used in this specification, it is explained that there are stated features, integral bodies, steps, operations, parts, assemblies and / or their groups, but it is not excluded that there are or add one or more other features, integral bodies, steps, operations, parts, assemblies and / or their groups. It should also be noted that, as used here, the terms "substantially", "approximately" and other similar terms are used as approximate terms and not as degree terms, so that they are used to explain the inherent deviations of the measured values, calculated values ​​and / or the values ​​provided that will be recognized by those of ordinary skill in the art.

[0023] It is difficult to detect problems in current air environment monitoring stations at the first time. In terms of problem diagnosis, it is usually dependent on manual analysis of monitoring data, which is inefficient and prone to misjudgment. Based on this, the present application provides an air environment monitoring station with a highly integrated intelligent monitoring system. Using sensors and monitoring equipment, real-time monitoring of the environment inside and outside the station can be achieved.

[0024] The sensing equipment may specifically include: Humidity sensing devices are distributed in multiple locations in the air environment monitoring station to monitor the ambient humidity of the air environment monitoring station. For example, multiple humidity sensing devices arranged outside the station building, together with humidity monitoring devices within 5-500 meters around the station building, form a humidity monitoring network, which can obtain real-time humidity changes in different areas around the station building 24 hours a day. These sensing devices are able to withstand severe weather conditions and provide accurate humidity readings.

[0025] Image acquisition devices are distributed at multiple locations outside the air environment monitoring station. The image acquisition devices can be high-resolution cameras and / or infrared cameras that operate around the clock to capture environmental changes or human activities that may be related to humidity anomalies.

[0026] Gas concentration monitoring equipment is distributed at multiple locations in the air environment monitoring station room to detect gas concentration data.

[0027] Equipment operation status monitoring equipment is distributed in multiple locations in the air environment monitoring station room to monitor the equipment in the monitoring station.

[0028] Through the Internet of Things technology, humidity monitoring, station building surrounding environment monitoring and various monitoring equipment inside the station building (such as gas concentration monitoring equipment, equipment operation status monitoring equipment, etc.) are organically connected.

[0029] In addition, servers and storage devices are also set up. The storage devices have sufficient data storage capacity to save the large amount of data collected from sensors and cameras. The servers have high performance to support real-time processing and analysis of data, supporting functions such as time series analysis, image recognition, and machine learning algorithms.

[0030] You can also set up communication equipment and establish a stable wireless network system to ensure seamless data transmission from sensors and cameras to the server. You can also set up network security equipment: deploy necessary network security measures to protect information security and privacy during data transmission.

[0031] A flowchart of a specific implementation method of the air environment monitoring station equipment monitoring method provided in this application is as follows Figure 1 As shown, the method includes: S101: Obtaining operating status data of air environment monitoring equipment.

[0032] Specifically, the operating status of the equipment inside the air environment monitoring station can be tracked and diagnosed in real time 24 hours a day through monitoring equipment.

[0033] S102: Determine whether the air environment monitoring device is in an abnormal state based on the operating status data. If it is determined that the air environment monitoring device is in an abnormal state, call the real-time image data collected by the image acquisition device.

[0034] In this step, the operating status data of the air environment monitoring equipment can be input into the fault diagnosis model to output a diagnosis result of whether the equipment is in an abnormal situation; the fault diagnosis model is based on big data analysis and machine learning technology, and is obtained by training large-scale training data including normal and abnormal situations.

[0035] By collecting historical data of the equipment's operating time, operating parameters (such as sensor sensitivity, response time, power consumption, etc.) and historical maintenance records; extracting features for predicting faults from these historical data, which may include parameter change trends, periodic changes, mutation points, etc. Select the ARIMA model for time series analysis, which is suitable for predicting continuous data with autoregressive characteristics. Use historical data to train the model and determine the model's parameters to fit the time series characteristics of the data. Input the real-time operating status data into the trained ARIMA model (autoregressive integrated moving average model) for prediction. If the deviation between the predicted value and the actual value exceeds a certain range, it is judged that there may be a fault trend.

[0036] S103: Perform image recognition on the real-time image data to detect whether there are people in the surrounding area of ​​the air environment monitoring device. If there are people, the real-time movement posture of the people is identified by detecting the positions of key joints of the people.

[0037] This step focuses on the spatial area around the air environment monitoring equipment and performs two detection tasks through a series of complex image processing and analysis algorithms. One task is to detect whether there are people around the equipment. This process involves the recognition and location of human targets in the monitoring image. The other task is to determine whether the person's action posture meets the characteristics of operating the air environment monitoring equipment.

[0038] The following methods can be used to perform image recognition to detect whether there is a person: Collect large-scale images of scenes including people and equipment, including different lighting conditions, different background environments, and various postures of people.

[0039] The collected images are annotated with data, and the annotated data includes whether there are people and their locations.

[0040] The labeled images and labeled data are used as training sets to train the model using convolutional neural network (CNN) to obtain a person recognition model.

[0041] The real-time image data is input into the personnel recognition model, and the position and confidence score of the personnel are output; when the confidence score is greater than a preset threshold When the device is in the vicinity of the environment, the recognition result indicating the presence of a person is output.

[0042] S104: Matching the recognized real-time motion posture of the person with a pre-established device operation behavior library to generate a matching result of whether the real-time motion posture of the person meets the characteristics of operating the air environment monitoring device.

[0043] Human body posture estimation technology is used to identify the key joint positions of the human body in the image (head, shoulders, elbows, hands, waist, knees, feet, etc.) based on the network model of joint point detection. Assume that the joint point position vector is ,By tracking and analyzing the positions of these joint points, a spatiotemporal feature model of human posture is constructed, so as to judge the real-time action posture of the person.

[0044] Among them, each standard posture model in the equipment operation behavior library is constructed based on the observation and data collection of personnel movements during the normal operation of the air environment monitoring equipment.

[0045] The construction of the standard posture model can be done as follows: Use image acquisition equipment to capture the action video of the operator when operating the air environment monitoring equipment normally. These action videos cover all relevant operation steps and common operation environments. Extract key frames from the video, which represent important actions or transition points in the operation process. Label each key frame to describe the operator's posture and action, such as the position of the hand, the tilt angle of the body, etc. Use deep learning convolutional neural network (CNN) to analyze and identify the standard posture of the operator, use the labeled posture data to train the model, learn to distinguish different operation postures, and automatically recognize these postures from new video data.

[0046] Specifically, obtain the real-time action posture feature vector of the person The real-time motion posture of the person includes the relative position and angle of key joints and their changes over time.

[0047] The recognized real-time personnel posture feature vector Standard operation posture feature vectors with device operation behavior library Compare and calculate the similarity between the two ; When the similarity between the two is greater than the similarity threshold, it is determined that the real-time action posture of the person matches the standard posture, and a matching result is generated that the real-time action posture of the person meets the characteristics of the operating air environment monitoring device; otherwise, a matching result is generated that the real-time action posture of the person does not meet the characteristics of the operating air environment monitoring device.

[0048] Image recognition technology is used to detect whether there are people around the device and whether the person's movements and postures meet the characteristics of operating the device. For example, if it is detected that someone is performing specific key operations in front of the device or using certain tools on the device (such as the appearance of maintenance tools such as wrenches, if they are within the monitoring field of view), it is determined that there may be a person operating the device. For example, for the switch operation of a specific device, the model library stores characteristic patterns such as the movement trajectory of the hand and the tilt angle of the body during normal operation. By comparing the actual detected person's posture with the degree of matching of these patterns, it is determined whether the person's movement posture meets the characteristics of operating the device.

[0049] S105: When the matching result is that the person's real-time motion posture does not conform to the characteristics of operating the air environment monitoring device, the historical operation and maintenance data and air monitoring data of the air environment monitoring device are called, and a diagnosis result is generated based on the correlation between the historical operation and maintenance data, the air monitoring data and the matching result.

[0050] The historical operation and maintenance data may specifically include the operation log, operation and maintenance record, and operation record of the equipment. Based on the correlation between the historical operation and maintenance data, air monitoring data, and matching results, a diagnosis result is generated, and response suggestions can be further given.

[0051] The process of combining historical operation and maintenance data, air monitoring data and matching results to obtain diagnostic results can be done in the following way: Integrate the operation logs, maintenance records, operation records, real-time image data, and air monitoring data of air environment monitoring equipment, and align the data based on timestamps. Collect data from various sources (equipment operation logs, maintenance records, operation records, real-time image data, and air monitoring data). Use timestamps to align all data to ensure the consistency of all information in time, facilitating accurate historical data analysis and real-time data processing.

[0052] Use algorithms based on association rule mining to mine the associations between data and determine the association rules related to equipment anomalies. Use association rule mining algorithms suitable for large data sets, such as Apriori or FP-Growth algorithms, to process and analyze data. Use Apriori or FP-Growth algorithms to identify frequent item sets and strong association rules, especially those related to abnormal equipment behavior or failures.

[0053] Based on the association rules, the historical operation and maintenance data, air monitoring data and matching results are analyzed to generate diagnostic results. According to the mined association rules, the relationship between the historical operation and maintenance data, air monitoring data and the matching results of real-time image data is analyzed. The association rule analysis results are combined with the historical failure modes and maintenance records of the equipment to generate specific fault diagnosis and recommended measures.

[0054] In addition, it may also include: using a causal reasoning model to determine the causal relationship between the operating error and the equipment abnormality, and generating the fault cause of the equipment abnormality caused by the operating error based on the inferred causal relationship; wherein the causal reasoning model is defined according to the variables studied and the expected causal relationship in the field of air environment knowledge, and is obtained by training using data including variables; generating response suggestions based on the fault cause, and using the fault cause and response suggestions as diagnostic results.

[0055] Among them, the causal reasoning model can use historical data to train the model and determine the model parameters to ensure that the causal relationship can be accurately inferred.

[0056] The embodiment of the present application can make the obtained diagnosis result more comprehensive and accurate by comprehensively analyzing multi-source data through correlation analysis, and can analyze the specific fault type and possible cause. Integrating multi-source data and applying advanced analysis can also quickly respond to changes in equipment and improve the efficiency of the entire monitoring system.

[0057] Based on any of the above embodiments, when the matching result is that the real-time action posture of the person does not conform to the characteristics of operating the air environment monitoring equipment, the evidence fixation event is automatically triggered: the historical operation and maintenance data and real-time image data of the time point corresponding to the non-conforming posture are written as evidence into an unchangeable storage medium for data storage, and a digital signature is added to the fixed evidence and a hash value is generated.

[0058] Once a gesture that does not meet the standards is detected, an evidence fixation event is immediately triggered. All key data related to that point in time is automatically intercepted from the system, including historical operation and maintenance data and real-time image data. The captured data is written to an unchangeable storage medium, such as a storage system with write-time encryption (WORM) or blockchain technology, to ensure that the data cannot be modified or deleted once written, which can effectively prevent data tampering. Add a digital signature to the fixed data to ensure the source and integrity of the data. Use a key management system to generate and manage signature keys to ensure the security of the keys. Generate a hash value for the stored data. The hash value serves as proof of data integrity and can be used to verify in the future whether the data has been tampered with. By using digital signatures and hash values, the security and trust of the data are increased, and any third party can verify its authenticity and integrity when obtaining the data.

[0059] When the above evidence fixation event is executed, an audit log for the evidence fixation event can also be generated synchronously. Automatically record all operation logs related to evidence data, including data access, query and any attempt to modify data, further improving system security.

[0060] Furthermore, the present application may also include: automatically generating a problem diagnosis report based on a report template using the collected evidence and diagnosis results to provide decision support for regulators.

[0061] According to the needs and usage scenarios of different users, this application pre-sets a variety of personalized report templates. For regulatory authorities, the report template focuses on the diagnosis results, impact scope, risk assessment and recommended measures of the problem, and uses concise and clear charts and text descriptions to facilitate regulators to make decisions quickly. For example, the surrounding environment of the station and the location of the interference source are displayed in the form of a map, the changes in monitoring data in different time periods are compared with bar charts, and serious abnormalities are highlighted with red warning signs. For operation and maintenance personnel, the report template pays more attention to the detailed operation status, fault analysis, maintenance suggestions and operation guides of the equipment, provides the technical parameters of the equipment, fault code interpretation and detailed description of the maintenance steps, and facilitates operation and maintenance personnel to maintain and manage the equipment. At the same time, users can flexibly select the display order, chart style, font size and other parameters of the report content through the system's template customization interface according to their special needs to achieve personalized report customization. Use template engine-based technologies, such as Velocity or Freemarker, to define different report templates. The template contains placeholders and variables for dynamically inserting specific data and analysis results. Users can select different template elements and parameter settings through a graphical interface to generate corresponding customized report templates according to user selections.

[0062] The report supports multiple output formats, including PDF (suitable for printing and archiving), Excel (convenient for further data analysis and processing), Word (convenient for text editing and reading), and other common formats. Users can view and download online through the system's web interface, or set up automatic sending of reports to a specified mailbox or integrate with other management systems. For example, after integration with the company's asset management system, when a station equipment fails, the relevant diagnostic report is automatically sent to the asset management system, triggering the equipment maintenance process, and displaying relevant prompt information on the interface of the asset management system to achieve data sharing and interaction and improve work efficiency. Use the document generation library and email sending library to achieve multiple output methods for reports. For integration with other systems, a Web Service or message queue-based method is used for data interaction and report delivery.

[0063] The report is presented in an intuitive and clear manner, allowing regulators to quickly understand the full picture of the problem and make decisions.

[0064] In addition, the present application also provides an air environment monitoring station equipment monitoring device, such as Figure 2 As shown in the structural block diagram of the air environment monitoring station equipment monitoring device, the device includes a memory 21 and a processor 22, and the memory 21 stores a computer program. When the computer program is executed by the processor 22, the air environment monitoring station equipment monitoring method described in any one of the above is implemented.

[0065] In addition, the present application also provides an air environment monitoring station, such as Figure 3 The deployment diagram of the air environment monitoring station is shown in the figure. The air environment monitoring station includes: Humidity sensing equipment, corresponding Figure 3 The humidity sensors are distributed at multiple locations in the air environment monitoring station.

[0066] Image acquisition device, corresponding to Figure 3 The cameras are distributed at multiple locations in the air environment monitoring station.

[0067] And according to the above-mentioned air environment monitoring station equipment monitoring device, corresponding to Figure 3 The core monitoring system in .

[0068] And a communication device (not shown in the figure) is used to communicate with the air environment monitoring station equipment monitoring device, and output the diagnosis result when the matching result is that the real-time action posture of the person does not meet the characteristics of operating the air environment monitoring equipment.

[0069] All data from IoT devices such as sensors and monitoring equipment are connected to the core monitoring system, i.e., the equipment monitoring device of the air environment monitoring station, for further analysis and processing.

[0070] In addition, the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements any of the above-mentioned air environment monitoring station equipment monitoring methods.

[0071] Computer readable storage media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0072] The professionals should also be further aware that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0073] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0074] The specific implementation methods described above further illustrate the purpose, technical solutions and beneficial effects of the present application in detail. It should be understood that the above description is only the specific implementation method of the present application and is not intended to limit the scope of protection of the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A method for monitoring equipment in an air environment monitoring station, characterized in that: The method comprises: Obtain operating status data of air environment monitoring equipment; Determine whether the air environment monitoring device is in an abnormal state based on the operating status data, and if it is determined that the air environment monitoring device is in an abnormal state, call the real-time image data collected by the image acquisition device; Perform image recognition on the real-time image data to detect whether there are people in the surrounding area of ​​the air environment monitoring equipment, and if there are people, identify the real-time movement posture of the people by detecting the positions of the key joints of the people; Matching the real-time motion posture of the identified personnel with a pre-established equipment operation behavior library to generate a matching result of whether the real-time motion posture of the personnel meets the characteristics of operating the air environment monitoring equipment; wherein each standard posture model in the equipment operation behavior library is constructed based on the observation and data collection of the personnel's motion during the normal operation of the air environment monitoring equipment; When the matching result is that the person's real-time motion posture does not conform to the characteristics of operating the air environment monitoring device, the historical operation and maintenance data and air monitoring data of the air environment monitoring device are called, and a diagnosis result is generated based on the correlation between the historical operation and maintenance data, the air monitoring data and the matching result.

2. The air environment monitoring station equipment monitoring method according to claim 1, characterized in that: The performing image recognition on the real-time image data to detect whether there are people in the surrounding area of ​​the air environment monitoring device includes: Collecting large-scale images of scenes including people and equipment, including different lighting conditions, different background environments, and various gestures of people; Annotate the collected images, including whether there are people and their locations; The labeled images and labeled data are used as training sets to train the model using convolutional neural network to obtain a person recognition model; The real-time image data is input into the personnel recognition model, and the position and confidence score of the personnel are output; when the confidence score is greater than a preset threshold, the recognition result that there is a person in the surrounding area of ​​the device is output.

3. The air environment monitoring station equipment monitoring method according to claim 1, characterized in that: The step of matching the identified real-time motion posture of the person with the pre-established device operation behavior library to generate a matching result of whether the real-time motion posture of the person meets the characteristics of operating the air environment monitoring device includes: Get the real-time action posture feature vector of the person ; The real-time motion posture of the personnel includes the relative position and angle of key joints and their changes over time; The recognized real-time personnel posture feature vector Standard operation posture feature vectors with device operation behavior library Compare and calculate the similarity between the two ; When the similarity between the two is greater than the similarity threshold, it is determined that the real-time action posture of the person matches the standard posture, and a matching result is generated that the real-time action posture of the person meets the characteristics of operating the air environment monitoring device; otherwise, a matching result is generated that the real-time action posture of the person does not meet the characteristics of operating the air environment monitoring device.

4. The air environment monitoring station equipment monitoring method according to claim 1, characterized in that: When the matching result is that the real-time motion posture of the person does not conform to the characteristics of operating the air environment monitoring device, calling the historical operation and maintenance data and air monitoring data of the air environment monitoring device, and generating a diagnosis result based on the association between the historical operation and maintenance data, the air monitoring data and the matching result includes: Integrate the operation logs, operation and maintenance records, operation records, real-time image data, and air monitoring data of air environment monitoring equipment, and align the data based on timestamps; Use an algorithm based on association rule mining to mine the association relationship between data and determine the association rules related to equipment anomalies; Based on the association rules, historical operation and maintenance data, air monitoring data and matching results are analyzed to generate diagnosis results.

5. The air environment monitoring station equipment monitoring method according to claim 4, characterized in that: Also includes: A causal reasoning model is used to determine the causal relationship between the operation error and the equipment abnormality, and based on the inferred causal relationship, the fault cause of the equipment abnormality caused by the operation error is generated; wherein the causal reasoning model is defined based on the variables studied and the expected causal relationship in the field of air environment knowledge, and is obtained by training using data including the variables; A response suggestion is generated according to the cause of the fault, and the cause of the fault and the response suggestion are used as the diagnosis result.

6. The air environment monitoring station equipment monitoring method according to any one of claims 1 to 5, characterized in that: Also includes: When the matching result is that the real-time motion posture of the person does not conform to the characteristics of operating the air environment monitoring equipment, the evidence fixation event is automatically triggered: The historical operation and maintenance data and real-time image data at the time point corresponding to the posture are written into an unchangeable storage medium as evidence for data storage, and a digital signature is added to the fixed evidence and a hash value is generated.

7. The air environment monitoring station equipment monitoring method according to claim 6, characterized in that: Also includes: An audit log for the evidence fixation event is simultaneously generated.

8. The air environment monitoring station equipment monitoring method according to any one of claims 1 to 5, characterized in that: The method of judging whether the air environment monitoring device is in an abnormal state based on the operating status data includes: The operating status data of the air environment monitoring equipment is input into the fault diagnosis model, and the diagnosis result of whether the equipment is in an abnormal situation is output; the fault diagnosis model is based on big data analysis and machine learning technology, and is obtained by training large-scale training data including normal and abnormal situations.

9. An air environment monitoring station equipment monitoring device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the air environment monitoring station equipment monitoring method according to any one of claims 1 to 8 is implemented.

10. An air environment monitoring station, characterized in that: include: Image acquisition devices are distributed at multiple locations of the air environment monitoring station; The air environment monitoring station equipment monitoring device according to claim 9; And a communication device is used to communicate with the air environment monitoring station equipment monitoring device, and output the diagnosis result when the matching result is that the real-time action posture of the person does not meet the characteristics of operating the air environment monitoring equipment.

Images